Anthropic · Model profile
Claude 4.1 Opus
Intelligence, Performance & Price Analysis
Source: Canonical slug: claude-4-1-opus-thinking · Canonical model registry at build time
Routing verdict
Frontier research / complex reasoning
Reserve this model for the hardest requests; simpler or repetitive work should stay on cheaper routes.
Claude 4.1 Opus summary metrics
- Intelligence
- 34 scoreClaude 4.1 Opus (Reasoning) scores 34 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other reasoning models in a similar price tier (median: 28).
- Speed
- 33.3 output tokens/secClaude 4.1 Opus (Reasoning) generates output at 33.3 tokens per second (based on Anthropic's API), which is at the lower end compared to other reasoning models in a similar price tier (median: 81.2 t/s).
- Latency
- 15.46s TTFTClaude 4.1 Opus (Reasoning) has a time to first token (TTFT) of 15.46s (based on Anthropic's API), which is at the higher end compared to other reasoning models in a similar price tier (median: 2.77s).
- Input Price
- $15.00 / 1M tokensClaude 4.1 Opus (Reasoning) costs $15.00 per 1M input tokens (at the higher end, median: $1.50) and $75.00 per 1M output tokens (at the higher end, median: $8.40), based on Anthropic's API.
- Output Price
- $75.00 / 1M tokensClaude 4.1 Opus (Reasoning) costs $15.00 per 1M input tokens (at the higher end, median: $1.50) and $75.00 per 1M output tokens (at the higher end, median: $8.40), based on Anthropic's API.
Assessment
Routing verdict and task fit
| Workload | Rating | Notes |
|---|---|---|
| Complex reasoning & agentic workflows | Optimal | Intelligence score 34 places this model among top performers. Suitable for multi-step analysis and agentic loops. |
| High-volume chat & customer-facing | Viable | Output speed may be a bottleneck for real-time chat at scale. |
| Latency-sensitive applications | Viable | TTFT 15.46s — latency may be noticeable in interactive use. |
| Cost-sensitive pipelines | Viable | Output pricing at $75.00 is premium. Route high-volume simple tasks to cheaper alternatives. |
Evidence
Evidence charts
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- Claude Opus 4.8 (max)55.7
- GPT-5.5 (xhigh)54.8
- Claude Opus 4.7 (max)53.5
- Claude Sonnet 5 (max)53.4
- GPT-5.5 (high)53.1
- GPT-5.4 (xhigh)51.4
- GLM-5.2 (max)51.1
- GPT-5.5 (medium)50.4
- Gemini 3.5 Flash50.2
- Claude Sonnet 4.6 (max)47.2
- Gemini 3.1 Pro Preview46.5
- Qwen3.7 Max46
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- GPT-5.5 (low)43.5
- Muse Spark43.1
- Kimi K2.7 Code41.9
- Claude Sonnet 5 (Non-reasoning)41.7
| Model | Artificial Analysis Intelligence Index by Open Weights / Proprietary |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| Claude Opus 4.8 (max) | 55.7 |
| GPT-5.5 (xhigh) | 54.8 |
| Claude Opus 4.7 (max) | 53.5 |
| Claude Sonnet 5 (max) | 53.4 |
| GPT-5.5 (high) | 53.1 |
| GPT-5.4 (xhigh) | 51.4 |
| GLM-5.2 (max) | 51.1 |
| GPT-5.5 (medium) | 50.4 |
| Gemini 3.5 Flash | 50.2 |
| Claude Sonnet 4.6 (max) | 47.2 |
| Gemini 3.1 Pro Preview | 46.5 |
| Qwen3.7 Max | 46 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| GPT-5.5 (low) | 43.5 |
| Muse Spark | 43.1 |
| Kimi K2.7 Code | 41.9 |
| Claude Sonnet 5 (Non-reasoning) | 41.7 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- Claude Opus 4.8 (max)55.7
- GPT-5.5 (xhigh)54.8
- Claude Opus 4.7 (max)53.5
- Claude Sonnet 5 (max)53.4
- GPT-5.5 (high)53.1
- GPT-5.4 (xhigh)51.4
- GLM-5.2 (max)51.1
- GPT-5.5 (medium)50.4
- Gemini 3.5 Flash50.2
- Claude Sonnet 4.6 (max)47.2
- Gemini 3.1 Pro Preview46.5
- Qwen3.7 Max46
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- GPT-5.5 (low)43.5
- Muse Spark43.1
- Kimi K2.7 Code41.9
- Claude Sonnet 5 (Non-reasoning)41.7
| Model | Artificial Analysis Intelligence Index |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| Claude Opus 4.8 (max) | 55.7 |
| GPT-5.5 (xhigh) | 54.8 |
| Claude Opus 4.7 (max) | 53.5 |
| Claude Sonnet 5 (max) | 53.4 |
| GPT-5.5 (high) | 53.1 |
| GPT-5.4 (xhigh) | 51.4 |
| GLM-5.2 (max) | 51.1 |
| GPT-5.5 (medium) | 50.4 |
| Gemini 3.5 Flash | 50.2 |
| Claude Sonnet 4.6 (max) | 47.2 |
| Gemini 3.1 Pro Preview | 46.5 |
| Qwen3.7 Max | 46 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| GPT-5.5 (low) | 43.5 |
| Muse Spark | 43.1 |
| Kimi K2.7 Code | 41.9 |
| Claude Sonnet 5 (Non-reasoning) | 41.7 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- GPT-5.5 (xhigh)54.8
- GLM-5.2 (max)51.1
- Gemini 3.5 Flash50.2
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- Muse Spark43.1
- Nemotron 3 Ultra37.8
- Grok 4.3 (high)37.6
- Claude 4.1 Opus (this model)33.7
- gpt-oss-120b (high)23.8
| Model | Intelligence |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| GPT-5.5 (xhigh) | 54.8 |
| GLM-5.2 (max) | 51.1 |
| Gemini 3.5 Flash | 50.2 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| Muse Spark | 43.1 |
| Nemotron 3 Ultra | 37.8 |
| Grok 4.3 (high) | 37.6 |
| Claude 4.1 Opus (this model) | 33.7 |
| gpt-oss-120b (high) | 23.8 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Output Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
- gpt-oss-120b (high)316 t/s
- Nemotron 3 Ultra248 t/s
- GLM-5.2 (max)216 t/s
- Qwen3.7 Max206 t/s
- Gemini 3.5 Flash192 t/s
- GPT-5.4 mini (xhigh)179 t/s
- GPT-5.4 (xhigh)168 t/s
- Grok 4.3 (high)164 t/s
- Gemini 3.1 Pro Preview152 t/s
- MiniMax-M395 t/s
- GPT-5.5 (xhigh)88 t/s
- Claude Sonnet 5 (max)84 t/s
- GPT-5.5 (low)82 t/s
- GPT-5.5 (high)81 t/s
- Grok Build 0.1 061681 t/s
- GLM-5.180 t/s
- Kimi K2.676 t/s
- GPT-5.5 (medium)73 t/s
- DeepSeek V4 Pro (max)72 t/s
- Claude Sonnet 4.6 (max)71 t/s
| Model | Output Speed |
|---|---|
| gpt-oss-120b (high) | 316 t/s |
| Nemotron 3 Ultra | 248 t/s |
| GLM-5.2 (max) | 216 t/s |
| Qwen3.7 Max | 206 t/s |
| Gemini 3.5 Flash | 192 t/s |
| GPT-5.4 mini (xhigh) | 179 t/s |
| GPT-5.4 (xhigh) | 168 t/s |
| Grok 4.3 (high) | 164 t/s |
| Gemini 3.1 Pro Preview | 152 t/s |
| MiniMax-M3 | 95 t/s |
| GPT-5.5 (xhigh) | 88 t/s |
| Claude Sonnet 5 (max) | 84 t/s |
| GPT-5.5 (low) | 82 t/s |
| GPT-5.5 (high) | 81 t/s |
| Grok Build 0.1 0616 | 81 t/s |
| GLM-5.1 | 80 t/s |
| Kimi K2.6 | 76 t/s |
| GPT-5.5 (medium) | 73 t/s |
| DeepSeek V4 Pro (max) | 72 t/s |
| Claude Sonnet 4.6 (max) | 71 t/s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Output speed context
- Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
- gpt-oss-120b (high)316 t/s
- Nemotron 3 Ultra248 t/s
- GLM-5.2 (max)216 t/s
- Gemini 3.5 Flash192 t/s
- Grok 4.3 (high)164 t/s
- MiniMax-M395 t/s
- GPT-5.5 (xhigh)88 t/s
- Kimi K2.676 t/s
- DeepSeek V4 Pro (max)72 t/s
- Claude Fable 5 (with fallback)71 t/s
- Claude 4.1 Opus (this model)33 t/s
| Model | Speed |
|---|---|
| gpt-oss-120b (high) | 316 t/s |
| Nemotron 3 Ultra | 248 t/s |
| GLM-5.2 (max) | 216 t/s |
| Gemini 3.5 Flash | 192 t/s |
| Grok 4.3 (high) | 164 t/s |
| MiniMax-M3 | 95 t/s |
| GPT-5.5 (xhigh) | 88 t/s |
| Kimi K2.6 | 76 t/s |
| DeepSeek V4 Pro (max) | 72 t/s |
| Claude Fable 5 (with fallback) | 71 t/s |
| Claude 4.1 Opus (this model) | 33 t/s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Output speed context
- Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
End-to-End Response Time
Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · Evaluation results measured independently by Artificial Analysis
- GPT-5.5 (low)6.12 s
- gpt-oss-120b (high)1.58 s
- Nemotron 3 Ultra2.02 s
- GLM-5.2 (max)2.31 s
- GPT-5.4 mini (xhigh)2.79 s
- GPT-5.5 (medium)6.88 s
- Qwen3.7 Max2.42 s
- Grok 4.3 (high)3.05 s
- Claude Opus 4.7 (max)8.86 s
- MiniMax-M35.25 s
- GPT-5.5 (high)6.15 s
- Claude 4.1 Opus (this model)15.03 s
- Gemini 3.1 Pro Preview3.3 s
- Gemini 3.5 Flash2.6 s
- Grok Build 0.1 06166.17 s
- Claude Opus 4.8 (max)7.75 s
- Kimi K2.7 Code9.59 s
- GLM-5.16.28 s
- Kimi K2.66.56 s
- DeepSeek V4 Pro (max)6.95 s
| Model | End-to-End Response Time |
|---|---|
| GPT-5.5 (low) | 6.12 s |
| gpt-oss-120b (high) | 1.58 s |
| Nemotron 3 Ultra | 2.02 s |
| GLM-5.2 (max) | 2.31 s |
| GPT-5.4 mini (xhigh) | 2.79 s |
| GPT-5.5 (medium) | 6.88 s |
| Qwen3.7 Max | 2.42 s |
| Grok 4.3 (high) | 3.05 s |
| Claude Opus 4.7 (max) | 8.86 s |
| MiniMax-M3 | 5.25 s |
| GPT-5.5 (high) | 6.15 s |
| Claude 4.1 Opus (this model) | 15.03 s |
| Gemini 3.1 Pro Preview | 3.3 s |
| Gemini 3.5 Flash | 2.6 s |
| Grok Build 0.1 0616 | 6.17 s |
| Claude Opus 4.8 (max) | 7.75 s |
| Kimi K2.7 Code | 9.59 s |
| GLM-5.1 | 6.28 s |
| Kimi K2.6 | 6.56 s |
| DeepSeek V4 Pro (max) | 6.95 s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Chart interpretation
- Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.
Latency: Time To First Answer Token
Seconds to first answer token received · Accounts for reasoning model 'thinking' time · Evaluation results measured independently by Artificial Analysis
- GPT-5.5 (low)0 s
- gpt-oss-120b (high)6.33 s
- GPT-5.5 (medium)0 s
- Nemotron 3 Ultra9.17 s
- GLM-5.2 (max)9.26 s
- GPT-5.4 mini (xhigh)0 s
- Qwen3.7 Max11.67 s
- Claude 4.1 Opus (this model)0 s
- Claude Opus 4.7 (max)0 s
- Grok 4.3 (high)0 s
- GPT-5.5 (high)0 s
- MiniMax-M320.98 s
- Grok Build 0.1 061624.67 s
- Gemini 3.1 Pro Preview0 s
- Gemini 3.5 Flash0 s
- Claude Opus 4.8 (max)0 s
- Kimi K2.7 Code42.73 s
- GLM-5.147.62 s
- Kimi K2.658.43 s
- DeepSeek V4 Pro (max)60.79 s
| Model | Latency: Time To First Answer Token |
|---|---|
| GPT-5.5 (low) | 0 s |
| gpt-oss-120b (high) | 6.33 s |
| GPT-5.5 (medium) | 0 s |
| Nemotron 3 Ultra | 9.17 s |
| GLM-5.2 (max) | 9.26 s |
| GPT-5.4 mini (xhigh) | 0 s |
| Qwen3.7 Max | 11.67 s |
| Claude 4.1 Opus (this model) | 0 s |
| Claude Opus 4.7 (max) | 0 s |
| Grok 4.3 (high) | 0 s |
| GPT-5.5 (high) | 0 s |
| MiniMax-M3 | 20.98 s |
| Grok Build 0.1 0616 | 24.67 s |
| Gemini 3.1 Pro Preview | 0 s |
| Gemini 3.5 Flash | 0 s |
| Claude Opus 4.8 (max) | 0 s |
| Kimi K2.7 Code | 42.73 s |
| GLM-5.1 | 47.62 s |
| Kimi K2.6 | 58.43 s |
| DeepSeek V4 Pro (max) | 60.79 s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Latency considerations
- Latency includes thinking / reasoning time when applicable. Lower is better for interactive use cases.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
- GPT-5.4 (xhigh)1.05M
- Gemini 3.5 Flash1M
- Claude Fable 5 (with fallback)1M
- GLM-5.2 (max)1M
- DeepSeek V4 Pro (max)1M
- Grok 4.3 (high)1M
- MiniMax-M31M
- Claude Opus 4.8 (max)1M
- Claude Opus 4.7 (max)1M
- Claude Sonnet 5 (max)1M
- Claude Sonnet 4.6 (max)1M
- Gemini 3.1 Pro Preview1M
- Qwen3.7 Max1M
- Claude Sonnet 5 (Non-reasoning)1M
- GPT-5.5 (xhigh)922k
- GPT-5.5 (high)922k
- GPT-5.5 (medium)922k
- GPT-5.5 (low)922k
- GPT-5.4 mini (xhigh)400k
- Nemotron 3 Ultra262.1k
| Model | Context Window |
|---|---|
| GPT-5.4 (xhigh) | 1.05M |
| Gemini 3.5 Flash | 1M |
| Claude Fable 5 (with fallback) | 1M |
| GLM-5.2 (max) | 1M |
| DeepSeek V4 Pro (max) | 1M |
| Grok 4.3 (high) | 1M |
| MiniMax-M3 | 1M |
| Claude Opus 4.8 (max) | 1M |
| Claude Opus 4.7 (max) | 1M |
| Claude Sonnet 5 (max) | 1M |
| Claude Sonnet 4.6 (max) | 1M |
| Gemini 3.1 Pro Preview | 1M |
| Qwen3.7 Max | 1M |
| Claude Sonnet 5 (Non-reasoning) | 1M |
| GPT-5.5 (xhigh) | 922k |
| GPT-5.5 (high) | 922k |
| GPT-5.5 (medium) | 922k |
| GPT-5.5 (low) | 922k |
| GPT-5.4 mini (xhigh) | 400k |
| Nemotron 3 Ultra | 262.1k |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Context window sizing
- Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
- DeepSeek V4 Pro (max)0.0063
- gpt-oss-120b (high)0.00454
- MiniMax-M30.0139
- Grok 4.3 (high)0.0101
- Kimi K2.7 Code0.0203
- GPT-5.5 (low)0.0475
- Grok Build 0.1 06160.0203
- GLM-5.10.0426
- Nemotron 3 Ultra0.0209
- Gemini 3.1 Pro Preview0.0329
- GPT-5.5 (medium)0.0754
- Kimi K2.60.0216
- GLM-5.2 (max)0.0268
- GPT-5.4 mini (xhigh)0.0215
- Gemini 3.5 Flash0.0884
- GPT-5.5 (high)0.0943
- GPT-5.5 (xhigh)0.107
- GPT-5.4 (xhigh)0.0722
- Qwen3.7 Max0.0343
- Claude Sonnet 4.6 (max)0.104
| Model | Cost per Intelligence Index Task |
|---|---|
| DeepSeek V4 Pro (max) | 0.0063 |
| gpt-oss-120b (high) | 0.00454 |
| MiniMax-M3 | 0.0139 |
| Grok 4.3 (high) | 0.0101 |
| Kimi K2.7 Code | 0.0203 |
| GPT-5.5 (low) | 0.0475 |
| Grok Build 0.1 0616 | 0.0203 |
| GLM-5.1 | 0.0426 |
| Nemotron 3 Ultra | 0.0209 |
| Gemini 3.1 Pro Preview | 0.0329 |
| GPT-5.5 (medium) | 0.0754 |
| Kimi K2.6 | 0.0216 |
| GLM-5.2 (max) | 0.0268 |
| GPT-5.4 mini (xhigh) | 0.0215 |
| Gemini 3.5 Flash | 0.0884 |
| GPT-5.5 (high) | 0.0943 |
| GPT-5.5 (xhigh) | 0.107 |
| GPT-5.4 (xhigh) | 0.0722 |
| Qwen3.7 Max | 0.0343 |
| Claude Sonnet 4.6 (max) | 0.104 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
- DeepSeek V4 Pro (max)$0.045
- gpt-oss-120b (high)$0.061
- MiniMax-M3$0.125
- Grok 4.3 (high)$0.139
- Nemotron 3 Ultra$0.244
- Kimi K2.6$0.346
- GLM-5.2 (max)$0.370
- Gemini 3.5 Flash$0.586
- GPT-5.5 (xhigh)$0.863
- Claude Fable 5 (with fallback)$2.75
| Model | Cost per Task |
|---|---|
| DeepSeek V4 Pro (max) | $0.045 |
| gpt-oss-120b (high) | $0.061 |
| MiniMax-M3 | $0.125 |
| Grok 4.3 (high) | $0.139 |
| Nemotron 3 Ultra | $0.244 |
| Kimi K2.6 | $0.346 |
| GLM-5.2 (max) | $0.370 |
| Gemini 3.5 Flash | $0.586 |
| GPT-5.5 (xhigh) | $0.863 |
| Claude Fable 5 (with fallback) | $2.75 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
- gpt-oss-120b (high)3.5
- DeepSeek V4 Pro (max)7.2
- MiniMax-M314.5
- Grok 4.3 (high)12.5
- GPT-5.5 (low)65.2
- Grok Build 0.1 061620
- Nemotron 3 Ultra33.5
- Kimi K2.7 Code24.3
- GLM-5.140.4
- Gemini 3.1 Pro Preview49
- GLM-5.2 (max)32.9
- Kimi K2.625
- GPT-5.5 (medium)98.8
- Gemini 3.5 Flash114
- GPT-5.4 mini (xhigh)21.9
- Qwen3.7 Max47.6
- GPT-5.5 (high)118.8
- GPT-5.4 (xhigh)88.5
- GPT-5.5 (xhigh)131.8
- Claude Sonnet 4.6 (max)149.3
| Model | Cost to Run Artificial Analysis Intelligence Index |
|---|---|
| gpt-oss-120b (high) | 3.5 |
| DeepSeek V4 Pro (max) | 7.2 |
| MiniMax-M3 | 14.5 |
| Grok 4.3 (high) | 12.5 |
| GPT-5.5 (low) | 65.2 |
| Grok Build 0.1 0616 | 20 |
| Nemotron 3 Ultra | 33.5 |
| Kimi K2.7 Code | 24.3 |
| GLM-5.1 | 40.4 |
| Gemini 3.1 Pro Preview | 49 |
| GLM-5.2 (max) | 32.9 |
| Kimi K2.6 | 25 |
| GPT-5.5 (medium) | 98.8 |
| Gemini 3.5 Flash | 114 |
| GPT-5.4 mini (xhigh) | 21.9 |
| Qwen3.7 Max | 47.6 |
| GPT-5.5 (high) | 118.8 |
| GPT-5.4 (xhigh) | 88.5 |
| GPT-5.5 (xhigh) | 131.8 |
| Claude Sonnet 4.6 (max) | 149.3 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
- Cache Hit
- Input
- Output
- gpt-oss-120b (high)$0.900
- DeepSeek V4 Pro (max)$1.31
- MiniMax-M3$1.56
- Grok Build 0.1 0616$3.20
- Nemotron 3 Ultra$3.60
- Grok 4.3 (high)$3.95
- Kimi K2.6$5.11
- Kimi K2.7 Code$5.11
- GPT-5.4 mini (xhigh)$5.33
- GLM-5.2 (max)$6.06
- GLM-5.1$6.06
- Qwen3.7 Max$10.25
- Gemini 3.5 Flash$10.65
- Claude Sonnet 5 (max)$12.20
- Claude Sonnet 5 (Non-reasoning)$12.20
- Gemini 3.1 Pro Preview$14.20
- GPT-5.4 (xhigh)$17.75
- Claude Sonnet 4.6 (max)$18.30
- Claude Opus 4.8 (max)$30.50
- Claude Opus 4.7 (max)$30.50
| Model | Cache Hit | Input | Output | Total |
|---|---|---|---|---|
| gpt-oss-120b (high) | $0.150 | $0.150 | $0.600 | $0.900 |
| DeepSeek V4 Pro (max) | $0.0036 | $0.435 | $0.870 | $1.31 |
| MiniMax-M3 | $0.060 | $0.300 | $1.20 | $1.56 |
| Grok Build 0.1 0616 | $0.200 | $1.00 | $2.00 | $3.20 |
| Nemotron 3 Ultra | $0.250 | $0.675 | $2.67 | $3.60 |
| Grok 4.3 (high) | $0.200 | $1.25 | $2.50 | $3.95 |
| Kimi K2.6 | $0.160 | $0.950 | $4.00 | $5.11 |
| Kimi K2.7 Code | $0.160 | $0.950 | $4.00 | $5.11 |
| GPT-5.4 mini (xhigh) | $0.075 | $0.750 | $4.50 | $5.33 |
| GLM-5.2 (max) | $0.260 | $1.40 | $4.40 | $6.06 |
| GLM-5.1 | $0.260 | $1.40 | $4.40 | $6.06 |
| Qwen3.7 Max | $0.250 | $2.50 | $7.50 | $10.25 |
| Gemini 3.5 Flash | $0.150 | $1.50 | $9.00 | $10.65 |
| Claude Sonnet 5 (max) | $0.200 | $2.00 | $10.00 | $12.20 |
| Claude Sonnet 5 (Non-reasoning) | $0.200 | $2.00 | $10.00 | $12.20 |
| Gemini 3.1 Pro Preview | $0.200 | $2.00 | $12.00 | $14.20 |
| GPT-5.4 (xhigh) | $0.250 | $2.50 | $15.00 | $17.75 |
| Claude Sonnet 4.6 (max) | $0.300 | $3.00 | $15.00 | $18.30 |
| Claude Opus 4.8 (max) | $0.500 | $5.00 | $25.00 | $30.50 |
| Claude Opus 4.7 (max) | $0.500 | $5.00 | $25.00 | $30.50 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Chart interpretation
- Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.
Time per Intelligence Index Task
Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better · Evaluation results measured independently by Artificial Analysis
- GPT-5.5 (low)0.421
- GPT-5.5 (medium)1.2
- Gemini 3.1 Pro Preview1.3
- Nemotron 3 Ultra1.4
- Qwen3.7 Max1.5
- Grok 4.3 (high)1.6
- gpt-oss-120b (high)1.9
- GPT-5.5 (high)2
- Gemini 3.5 Flash2.2
- GLM-5.2 (max)2.8
- GPT-5.5 (xhigh)3
- GPT-5.4 (xhigh)3.1
- Grok Build 0.1 06163.8
- MiniMax-M34
- Claude Fable 5 (with fallback)4.8
- Kimi K2.7 Code5
- GLM-5.15.1
- Claude Opus 4.7 (max)5.9
- DeepSeek V4 Pro (max)6.7
- Claude Opus 4.8 (max)6.8
| Model | Time per Intelligence Index Task |
|---|---|
| GPT-5.5 (low) | 0.421 |
| GPT-5.5 (medium) | 1.2 |
| Gemini 3.1 Pro Preview | 1.3 |
| Nemotron 3 Ultra | 1.4 |
| Qwen3.7 Max | 1.5 |
| Grok 4.3 (high) | 1.6 |
| gpt-oss-120b (high) | 1.9 |
| GPT-5.5 (high) | 2 |
| Gemini 3.5 Flash | 2.2 |
| GLM-5.2 (max) | 2.8 |
| GPT-5.5 (xhigh) | 3 |
| GPT-5.4 (xhigh) | 3.1 |
| Grok Build 0.1 0616 | 3.8 |
| MiniMax-M3 | 4 |
| Claude Fable 5 (with fallback) | 4.8 |
| Kimi K2.7 Code | 5 |
| GLM-5.1 | 5.1 |
| Claude Opus 4.7 (max) | 5.9 |
| DeepSeek V4 Pro (max) | 6.7 |
| Claude Opus 4.8 (max) | 6.8 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Specifications
Architecture and limits
| Specification | Value | Source |
|---|---|---|
| Model type | Proprietary | faq |
| Reasoning | Yes | faq |
| Input modalities | Claude 4.1 Opus (Reasoning) supports text and image input. | faq |
| Output modalities | Claude 4.1 Opus (Reasoning) supports text output. | faq |
| Context window | 200k tokens | faq |
| Open weights / source | No, Claude 4.1 Opus (Reasoning) is proprietary. The model weights are not publicly available. | faq |
| Parameters | Claude 4.1 Opus (Reasoning) is a proprietary model and Anthropic has not disclosed the model size or parameter count. | faq |
| Knowledge cutoff | Claude 4.1 Opus (Reasoning) has a knowledge cutoff of March 2025. The model's training data includes information up to this date. | faq |
| API availability | Yes, Claude 4.1 Opus (Reasoning) is available via API through 4 providers. | faq |
Method
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for Claude 4.1 Opus.
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Questions
Model FAQ and technical disclosures
Models
Related
- 01AnthropicOther Anthropic models in the catalog.
- 02LeaderboardsCertified metric ranks, when published.